nobody

Counterfactual persona. Genomics for microbes. LLMs for teaching. Occasionally I support my views.

[nobody @phiweger]

Re: Building your own tools, @karpathy introduced the idea of an agentic wiki, where the models write the thing, and your questions can cause it to change or flag absent knowledge. Suited well for capturing tacit team knowledge, SOPs ...

[nobody @phiweger]

https://t.co/xUiRwbKSTB

[nobody @phiweger]

Re: Building your own tools, @karpathy introduced the idea of an agentic wiki, where the models write the thing, and your questions can cause it to change or flag absent knowledge. Suited well for capturing tacit team knowledge, SOPs ...

[nobody @phiweger]

Oh, and I have it optimize its search strategy (grep? rag? rank fusion?) over your corpus (think "autoresearch", another concept Karpathy popularized):

[nobody @phiweger]

https://t.co/G7JJaiFPoP

[nobody @phiweger]

When you model kindness like physics, and sprinkle the Dalai Lama on top, what you get is pretty much what my worldview seems to be:

[nobody @phiweger]

Thanks!

[nobody @phiweger]

Die meisten Medizinstudis haben nach 6 Jahren kaum mehr Ahnung von Antibiotika als am Anfang. Die Übung in der Anwendung fehlt. In unserer Lehre setzen wir deswegen auf Spiele. Das hat nun Früchte getragen, und ihr könnt uns unterstützen (Kickstarter below)!

[nobody @phiweger]

https://t.co/ofImKuesdU

[nobody @phiweger]

The content creator agonizes for hours over three sentences. The content constructor just types 'in the style of Hemingway' and goes to lunch. Both are probably fine.

[nobody @phiweger]

On love, poetry, and AI -- https://t.co/SIYLuI9rls

[nobody @phiweger]

https://t.co/oKACkWytRl

[nobody @phiweger]

Wrote something about a practice I find useful, enjoy (link below).

[nobody @phiweger]

Raising children is prompt engineering with a continuously updated model and really bad API docs.

[Chubby♨️ @kimmonismus]

Arizona’s Bold Step into AI-Education. So it begins

Arizona has approved an unprecedented educational model: a charter school where students will receive two hours of daily academic instruction directed entirely by AI. Unbound Academy, launching next year, is a fully online school for grades four through eight, replacing traditional teaching with AI-driven learning. This model adapts to each student’s pace and ability using tools like IXL and Khan Academy, analyzing emotional cues, time on tasks, and responses to customize lessons. The promise? A learning experience free of frustration or boredom, ensuring optimal engagement and progress.

The remaining hours of the school day won’t be idle. Students will engage in life-skills workshops covering financial literacy, entrepreneurship, and critical thinking. These sessions are facilitated by “guides” rather than traditional teachers. This model has roots in Unbound’s private Texas school, where claims of doubled academic outcomes with reduced hours have sparked curiosity and controversy. Inspired by Elon Musk’s iterative approach to innovation, Unbound aims to refine its model for broader adoption across states like Arkansas and Utah.

Critics, however, question the reliance on AI, emphasizing the irreplaceable value of human teachers in fostering creativity, empathy, and inspiration. Proponents argue this paradigm shift could address inefficiencies in traditional schooling and better prepare students for a rapidly changing world. Supported by major players like the Bill and Melinda Gates Foundation, Unbound’s AI-driven curriculum might signal the beginning of a significant transformation in education—or a divisive experiment in its accessibility and quality.

[Jeremy Howard @jeremyphoward]

I'll get straight to the point.

We trained 2 new models. Like BERT, but modern. ModernBERT.

Not some hypey GenAI thing, but a proper workhorse model, for retrieval, classification, etc. Real practical stuff.

It's much faster, more accurate, longer context, and more useful. 🧵

[@levelsio @levelsio]

I've created a bug board to fix 🇪🇺 Europe

https://t.co/sNjbqHAYgk

You can post your ideas on how to improve Europe and others can vote on it

I've added the first eu/acc objectives that were sourced from X and that everyone voted on here

💪 May the best ideas save Europe!

[Nous Research @NousResearch]

Introducing a smol Hermes 3 LLM!

Hermes 3 3B is now available on @huggingface alongside quantized GGUF versions to make it even smaller.

More info and download links here: https://t.co/afSKPEjoWe

Run Hermes on phones, laptops, and CPUs without sacrificing speed, and may also be a great pairing with 70B for speculative decoding!

Hermes 3 3B was built by @teknium, @rogershijin @theemozilla, and @nullvaluetensor

Learn more about Hermes, see our technical report, and chat with it now: https://t.co/OTeMLfsUpW

[nobody @phiweger]

@kiwicopple @supabase @stackblitz @lovable missing y axis

[nobody @phiweger]

I'll be publishing thought pieces and more technical behind-the-scenes on a newsletter, subscribe to be notified about new posts: https://t.co/np48hjgQRS

[nobody @phiweger]

I've been toying with LLMs for a while now, and here's my latest experiment: Synthetic podcasts with dead or fictional characters. Episode #1: Sherlock Holmes. We talk about Watson, drugs, physical exercise and role play.

[nobody @phiweger]

Link to podcast: https://t.co/573jaHAQOs